{"id":"W4414978537","doi":"10.1145/3763128","title":"TraceLinking Implementations with Their Verified Designs","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"TRACE (psycholinguistics); Compiler; Correctness; Modular design; Tracing; Verifiable secret sharing; Debugging; Semantics (computer science); Implementation; Signature (topology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005886693,0.0001278005,0.0001291802,0.0001199776,0.0002043256,0.0001654158,0.002445798,0.0000410354,0.000002004757],"category_scores_gemma":[0.000601781,0.00007866908,0.00005693239,0.0007817633,0.00007697198,0.0003674669,0.0004371947,0.000149953,9.797958e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000390156,"about_ca_system_score_gemma":0.00004010633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001327843,"about_ca_topic_score_gemma":0.000002575392,"domain_scores_codex":[0.9990743,0.00001647072,0.0002114661,0.000258547,0.0002171847,0.0002219876],"domain_scores_gemma":[0.9989318,0.0001044451,0.0002081841,0.0005645402,0.0001667845,0.00002428783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004448198,0.0001333784,0.004592626,0.0001656331,0.00007875748,4.190711e-7,0.006560785,0.00002034654,0.03462457,0.5361536,0.0003609617,0.4172645],"study_design_scores_gemma":[0.0006954733,0.0003755353,0.01054355,0.0004922076,0.00005378891,0.00001159709,0.006930058,0.001145722,0.9574184,0.01591976,0.006098991,0.00031488],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7525032,0.0003638364,0.2262235,0.007727615,0.0004459146,0.002043655,0.00000581532,0.0008309893,0.009855526],"genre_scores_gemma":[0.4699872,0.000003706318,0.5296928,0.0001316119,0.00001234034,0.00006817364,4.704445e-7,0.000006055062,0.00009768044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9227939,"threshold_uncertainty_score":0.4544942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03409471806375904,"score_gpt":0.3255725245977236,"score_spread":0.2914778065339646,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}